# GPT-4o Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/gpt-4o?page=2
> Markdown URL: https://aitinkerers.org/technologies/gpt-4o.md?page=2
> Technology record last updated: 2026-02-22T16:41:33Z
> Generated: 2026-08-25T20:16:07Z

GPT-4o (omni) is OpenAI's flagship multimodal model: it delivers GPT-4 intelligence with native, real-time processing across text, audio, and vision.

This is GPT-4o, OpenAI’s 'omni' model: a single neural network natively handling text, audio, and image inputs and outputs. It matches GPT-4 performance on English text and code, but surpasses it on non-English language, vision, and audio benchmarks. The speed is a major upgrade: it achieves human-level responsiveness in voice, with an average response time of 0.32 seconds (a significant jump from GPT-4’s 5.4 seconds). Developers get a 128K token context window and a model that is more cost-efficient than its predecessor, making high-intelligence, real-time applications viable.

- Official technology site: https://openai.com/index/hello-gpt-4o
- Public AI Tinkerers demos and talks: 57
- Result page: 2 of 3

## Recent Public Talks and Demos

### [“Where Did My Money Go?” - Reconciling Ecomm Sales with LLMs, Not Spreadsheets](https://toronto.aitinkerers.org/talks/rsvp_OYdYkJXeDdA)

Every Shopify store owner has faced this mystery: “I sold $6,400, but only $3,900 showed up in my bank account. What happened and Why?” Well, it is because of Stripe fees, customer returns, chargebacks, withholding..etc. We can spend hours to use spreadsheet and complicated formula to match numbers and figure out the difference (the current way) or there must be a better way! In this demo, I’ll show how we’re building an AI agent that can actually reason through transaction data, trace the money trail, and explain where every dollar went—like a forensic accountant, it's faster and no spreasheet. I’ll show the model live digging into real reconciliation logic, identifying discrepancies, and even suggesting follow-up actions. I have only 1 slide to visualize the problem, and then just raw code, live execution and logs to demo whether an (confused) AI agent can really be an accountant.

- Event context: AI Tinkerers Toronto - April 2025 Meetup at Shopify — 2025-04-24 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_OYdYkJXeDdA

### [epilepsy ally: a chatbot to help parents of kids with epilepsy](https://chicago.aitinkerers.org/talks/rsvp__O0u3ll2BrE)

Some kids have seizures that cannot be stopped with medicine - for many, brain surgery is the only option. As a parent of a child with intractable epilepsy, I have found it daunting to figure out what my child needs. I built a chatbot that sifts through medical jargon and the latest research and helps parents who are facing or who's child has already had surgery.

- Event context: AI Tinkerers Chicago April Meetup — 2025-04-15 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp__O0u3ll2BrE

### [Facilitando el proceso de selección y pruebas técnicas.](https://medellin.aitinkerers.org/talks/rsvp_KW4pppbunGQ)

Este agente aprovecha la tecnología de modelos de lenguaje extensos (LLM) para facilitar el proceso de selección y evaluación. Analiza las hojas de vida recibidas, asignando un puntaje del 1 al 10 en función de la coherencia con el perfil requerido. Además, evalúa las pruebas técnicas enviadas, transcribe los videos de las entrevistas y realiza un análisis de sentimientos para ofrecer una visión integral del desempeño de los candidatos. Aquí está el desglose de los puntos más importantes del proceso, centrando en el nodo que actúa como agente: Inicialización de Campos: Este primer paso es crucial, ya que configura el entorno para que el sistema pueda trabajar con los datos provenientes de las hojas de vida. Los campos se inicializan para capturar la información relevante de cada candidato, como nombre, experiencia laboral, educación, habilidades, etc. Extracción de Información del PDF: El flujo extrae la información de la hoja de vida en formato PDF. Este es el nodo que actúa como el agente del proceso. Utiliza un modelo de extracción de texto para identificar y extraer los datos relevantes del archivo PDF, transformando los datos no estructurados en una forma procesable. Validación de la Información (Validación de la Hoja de Vida): Una vez extraída la información, el sistema la valida según los criterios establecidos para el puesto. Este paso es fundamental para asegurar que solo las hojas de vida que cumplen con los requisitos sean procesadas. El flujo puede incluir validaciones como experiencia mínima, títulos académicos relevantes o habilidades específicas. Guardar los Resultados en Google Sheets: Los resultados de la evaluación (la calificación del CV) se almacenan en una hoja de cálculo de Google Sheets. Esto permite mantener un registro organizado de todos los candidatos y sus calificaciones, lo que facilita la revisión y el análisis posterior de los resultados. Almacenamiento en Carpeta por Proceso: Para mantener todo bien organizado, el flujo crea una carpeta en Google Drive, o verifica si ya existe, y guarda el documento de la hoja de vida evaluada dentro de esa carpeta específica del proceso de contratación. Esto asegura que cada proceso tenga su propia carpeta de documentación, lo que facilita el acceso y la gestión de los documentos asociados. Manejo de Errores: Si algo falla durante el proceso, como no poder extraer información del PDF o si el candidato no pasa la validación, el sistema genera un mensaje de error y lo comunica automáticamente, indicando la causa del problema. Nodo Actuando como Agente: El nodo que actúa como agente es el encargado de la extracción de la información del archivo PDF. Este nodo utiliza un modelo especializado (probablemente basado en NLP o procesamiento de lenguaje natural) para analizar el contenido del CV y extraer los datos relevantes de manera automática. A través de este proceso, el sistema obtiene datos clave como: Nombre Experiencia laboral Formación académica Habilidades Otros detalles relacionados Este es el punto más crucial del proceso porque, sin la correcta extracción y organización de los datos, no sería posible realizar la evaluación y validación del CV.

- Event context: AI Tinkerers Medellín #11 - Science Fair - Agentes en acción — 2025-04-01 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_KW4pppbunGQ

### [Live LLM and AI streaming workflow with Python](https://boston.aitinkerers.org/talks/rsvp_4hO81o8z310)

We will be working with async and streaming requests and responses from both hosted AI APIs and self-hosted LLMs to enhance the python development workflow. For example, we can avoid using ChatGPT for more explicit prompting being streamed directly in your python interpreter. We will most likely use AI21 Lab’s AI API and model weights for the demo, though we can be AI model agnostic.

- Event context: AI Tinkerers Boston March Meetup - AI21 Labs Takeover! — 2025-03-24 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_4hO81o8z310

### [Mobile Use Agent - Operator for apps](https://delhi.aitinkerers.org/talks/rsvp_UY-xVS4lLCY)

Imagine an AI operator that doesn't just navigate Chrome or web apps — it seamlessly operates mobile applications, executing tasks, automating workflows, and interacting with interfaces just like a human user. In this live demo, I'll showcase a mobile-use agent that leverages computer vision, touch emulation, and intelligent decision-making to operate mobile apps. This AI agent can handle real-world tasks across various mobile apps. I'll dive into the code, architecture, and challenges faced in building this operator.

- Event context: AI Tinkerers - Delhi Inaugural Meetup (March) — 2025-03-22 — Delhi
- Public talk page: https://delhi.aitinkerers.org/talks/rsvp_UY-xVS4lLCY

### [Accounting AI agent under the hood](https://london.aitinkerers.org/talks/rsvp_S55z1tqepaw)

Demo of accounting AI agent that is completing bookkeeping workflow. Includes - extensive examples of chain of thought, few shots and other prompting techniques - RAG & choice of vector DB & choice of embedding model - examples of formal verification - application of standard model (gpt-4o), and test time model (o1), sharing benefits of each

- Event context: AI Tinkerers London - March Meetup — 2025-03-20 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_S55z1tqepaw

### [Using AI to make Mood-based Music Recommendations](https://nyc.aitinkerers.org/talks/rsvp_Fs7Kn5C2DxM)

Jammy is an iOS app that helps you process your mood with music that has helped others. Chat privately with Jammy to get personalized, mood-based playlist recommendations for clarity, calm, and confidence anytime.

- Event context: AI Tinkerers NYC Meetup - March 2025 Sponsored by SignalFire and Comet — 2025-03-04 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_Fs7Kn5C2DxM

### [Agent Laboratory: Agentic AI Researcher](https://prague.aitinkerers.org/talks/rsvp_2skAj-j5HIE)

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas. Agent Laboratory consists of specialized agents driven by large language models to support you through the entire research workflow—from conducting literature reviews and formulating plans to executing experiments and writing comprehensive reports.

- Event context: AI Tinkerers Prague - February 2025 Meetup — 2025-02-25 — Prague
- Public talk page: https://prague.aitinkerers.org/talks/rsvp_2skAj-j5HIE

### [Comparing Multimodal AI on Analytical Reasoning](https://boston.aitinkerers.org/talks/rsvp_j5G8xNtOHV0)

Many different deep learning models, especially LLMs, can be focused and fine-tuned on specific data modals. One very interesting feature of today's LLMs is multimodal input; this has its uses in encoding image, text, structured, and other sorts of data into the same embedding space. This talk will briefly go over the technical use cases of multimodal models by running an in-code comparison across different AI models and their ability to analyze and reason with data.

- Event context: AI Tinkerers Boston February 2025 — 2025-02-24 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_j5G8xNtOHV0

### [AI Startup Scout](https://seattle.aitinkerers.org/talks/rsvp_09B1h3d1O3M)

One piece of a multi agent architecture that helps me, a venture capitalist, to identify compelling new companies and meet them. In this demo I will show the sub-agent that reads Hacker News to identify which stories *could correspond to compelling startups, and then enriches those stories with (1) information about the founders from an external source and (2) synthesis about why this might be an interesting company. Given my areas of focus change periodically, I split the prompt into a baseline configuration prompt, and a focus area prompt

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_09B1h3d1O3M

### [OCR? More Like OMG: When AI Can’t Handle Your PDFs](https://seattle.aitinkerers.org/talks/rsvp_p-sPN1uL3-M)

From doing evals while building Paper2Audio, we have a growing collection of pages from PDFs that models are are having a hard time understanding. There are some really epic fails! We'll show the most interesting problems we've found, and different ways we've found to solve some of them. We'll compare popular, general models, like GPT-4o and Gemini Flash 2.0 (which we've found generally works better at 4% of the cost), as well as some more specialized models people will be less familiar with, like MinerU and Marker. One thing to clarify- this won't be a demo of Paper2Audio generally, since I think the PDF understanding part is what will be most interesting to everyone at AI Tinkerers.

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_p-sPN1uL3-M

### [LLMs can teach themselves to better predict the future](https://seattle.aitinkerers.org/talks/rsvp_zkiKbBlvnuQ)

In our first paper from Lightning Rod Labs (https://lightningrod.ai), we explore if AI can improve its forecasts via self-play and real-world outcomes: - 12,100 questions and outcomes from Polymarket (politics, sports, crypto, science, etc) - Base model generates multiple distinct reasoning traces and predictions per question - Rank predictions by how close they were to the actual outcome - Fine-tune with DPO on the ranked traces & predictions Result: +7-10% accuracy over control, bringing two small (14B) models on par with GPT-4o (over 10x larger). Arxiv Link: https://arxiv.org/abs/2502.05253

- Event context: AI Tinkerers Seattle - February 2025 Meetup — 2025-02-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_zkiKbBlvnuQ

### [How I used Microsoft’s New Phi-4 SLM with unsloth to Finetune & Predict User Responses (Classification Tasks)](https://abu-dhabi.aitinkerers.org/talks/rsvp_gNRNflVanDY)

Chatbot Arena is a platform developed by the UC Berkeley Sky Computing Lab, designed to benchmark and compare large language models (LLMs) through anonymous, randomized battles. It employs a crowdsourced approach where users can ask questions and vote for their preferred responses. For example, consider this scenario: a user asks a question to the LLMs (e.g., ChatGPT, Claude.ai, Llama, etc.), and two different responses are returned. Which of the two responses would the user choose and prefer? This is an interesting problem as it intersects machine learning and behavioral psychology. To predict user choices with a reasonable level of success, the predictive model must analyze patterns in user behavior and preferences. Phi-4, Microsoft’s new 14B model, which performs on par with OpenAI’s GPT-4o-mini, is now available. This demo aims to explore Phi-4's capability to understand text content and perform analyses based on it. Specifically, it will demonstrate how Phi-4 can analyze the user’s question, evaluate two response options, and predict which response the user is most likely to choose. This demo will cover: Setting up and loading the Phi-4 model. Crafting prompt instructions to generate new synthetic features. Making predictions on user responses based on specifically defined criteria. Using Phi-4 to predict user responses based on the provided criteria. Streaming the predicted output as it is generated by Phi-4.

- Event context: AI Tinkerers - Abu Dhabi Meetup #2 (Jan 2025) — 2025-01-17 — Abu Dhabi
- Public talk page: https://abu-dhabi.aitinkerers.org/talks/rsvp_gNRNflVanDY

### [Camera-Based Travel Assistant](https://singapore.aitinkerers.org/talks/rsvp_C8NmO1pKDH0)

I built an app with AI, and would like to share what I learnt from it, and hear feedback on my learnings. The app: Web app whose homepage is device camera. Taking a picture prompts GPT to describe what's in the image, and provide helpful advice when the image is of a landmark or food, which can be helpful when one is travelling. Images are saved in a history drawer that can be returned to. Opening on phone allows switching between back and front cameras. The presentation: Technical demo demonstrating how I used Next's Route Handlers and Vercel's AI SDKs to stream responses from OpenAI's Chat Completions API to client, and how I used Cursor to build the camera UI and write tests.

- Event context: AI Tinkerers Singapore: 4th Meetup - January 10th, 2025 — 2025-01-10 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_C8NmO1pKDH0

### [ChatOne](https://seattle.aitinkerers.org/talks/rsvp_2pUjkIFnGVg)

ChatOne is an experimental platform that democratizes access to large language models (LLMs) by making them accessible through SMS and phone calls. Designed for regions and demographics with limited internet access, ChatOne ensures AI reaches underserved populations. This project explores how AI can learn from diverse cultures, reducing biases that arise when AI systems primarily interact with internet-rich environments.

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_2pUjkIFnGVg

### [MixedVoices: Tracking and Improving Voice Agents](https://bengaluru.aitinkerers.org/talks/rsvp_VH5ioEeVmJ4)

MixedVoices is an open source analytics and testing platform for voice agents. It helps builders track, visualize, and optimize performance by view conversation flowcharts, running simulations and suggesting prompt improvements. Technical Details: - LLM chain of thought to break calls into reusable and deterministic steps - Diarization of audio: Still not solved, accuracy of current solutions is still subpar, using stereo audio instead - Emotion analysis: gpt4o (hume planned later) - Using flowcharts to condense 1000s of recordings and create simulations that cover all edge cases - Creating simulations to test agent on, ensuring entire graph is covered Demo Structure: - My experience in building Voice agents and facing problems due to unreliability - Project walk through: Python API (Few lines of code to integrate) + Streamlit Dashboard (Runs locally) - Importance of Version control to track agent evolution over time - Examples of edge cases discovered - Examples of simulations and how they help in continuous evaluation

- Event context: AI Tinkerers Bengaluru - December - RSVP REQUIRED — 2024-12-05 — Bengaluru
- Public talk page: https://bengaluru.aitinkerers.org/talks/rsvp_VH5ioEeVmJ4

### [GPT-4 Gets Physical: Building a Language-Guided Service Robot](https://palo-alto.aitinkerers.org/talks/rsvp_-fRGIhqZIqI)

We gave a robot body to a GPT-4o AI agent. Here serving a glass from a human to another🍹 With only: • 30mn of arm demonstrations • A language prompt to guide it You can also teach it to clean, play, check in on you. What would you teach it?

- Event context: AI Tinkerers - Palo Alto - November 2024 Meetup — 2024-11-21 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_-fRGIhqZIqI

### [Build powerful domain specific AI agent with transfer learning techniques.](https://atlanta.aitinkerers.org/talks/rsvp_Bo4QtaFLs9o)

We tried to improved our Engineer Agent after the released of GPT-4o Paradoxically, while the reasoning of frontier models surpass humans on many complex math, coding or science problems, they fail at performing the simplest workflows - without a Human guiding the AI. Why? Because general purpose LLMs are not trained on the right type of data to make domain specific autonomous agents. I then went the extra miles to develop technics and system to enable universal and autonomous agents - but also train the models and generate the synthetic data needed to achieve our engineering task.

- Event context: AI Tinkerers Atlanta October Meetup — 2024-10-21 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_Bo4QtaFLs9o

### [Dialoguing with Hugging Face's LLMs](https://paris.aitinkerers.org/talks/rsvp_NqwWdDTv8vU)

We are currently developing an experimental project: speech-to-speech. This library, still under development, offers a modular approach to speech-to-speech language models through a pipeline that includes speech-to-text, large language model prompting, and text-to-speech. The pipeline is fully open and modular, with a focus on leveraging models available via the Transformers library on the Hugging Face hub. While current approaches tend to focus on end-to-end models, often citing latency benefits, we have achieved a latency of around 500ms with a few technical tweaks. Moreover, the modular approach allows users to easily switch components: for example, swapping the Gemma 2B model for LLaMA 3.1 8B can be done directly from the CLI.

- Event context: AI Tinkerers - Paris Meetup on October 15th — 2024-10-15 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_NqwWdDTv8vU

### [Multiple agents, voice and text AIs](https://la.aitinkerers.org/talks/rsvp_tmwbJSZcjJI)

Current project that I am building incorporates Claude, gpt-4o and gemini AIs to collaborate together. This tool helps users create documents (newsletters specifically) using only their voice in a conversational manner. They can create, brainstorm, and edit it all with the voice.

- Event context: Aug 28th - LA AI Tinkerers Meetup & Demos — 2024-08-29 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_tmwbJSZcjJI

### [Using Agentic workflows to unlock the performing arts](https://berlin.aitinkerers.org/talks/rsvp_6oF4LAPy1dE)

We are building as part of a team-based AI project, an agentic workflow to scan the web, compile cultural events of all types, and generate a listing using LLMs (GPT-4o-mini and LLama-3-8B) to parse the contents. The aim is to promote live performing arts events and make them more accessible to the general public. Parsing event webpages is complex and currently existing search engines or AI searches are very poor at providing bookable links. Therefore we are investigating the use of fine-tuning to speed up the link extraction, and working on improving generic agentic skills to use by the agents to parse event calendars.

- Event context: AI Tinkerers Berlin - August 22 — 2024-08-22 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_6oF4LAPy1dE

### [Building blocks for voice-to-voice AI](https://sf.aitinkerers.org/talks/rsvp_OaIp4wdokw0)

Building fast, reliable conversational voice bots on top of today's generative AI models and tooling requires combining a number of technologies. Major components include network transport, audio compression and processing, text-to-speech, multi-turn LLM inference, speech-to-text, tool use, and interruption handling. We'll start with a demo of a voice bot built with Open Source libraries running at 500ms voice-to-voice latency. Then we will do a lightning tour of the demo bot's components and 50 core lines of code.

- Event context: AI Tinkerers - San Francisco - August 2024 Meetup — 2024-08-22 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_OaIp4wdokw0

### [Transforming Code Collaboration with Aider: AI-Powered Pair Programming](https://fort-wayne.aitinkerers.org/talks/rsvp_fd5h26pQoac)

Meet Aider —an open-source tool that's redefining how developers work with large codebases. Aider seamlessly integrates with Git, leveraging AI models like GPT-4o and Claude Sonnet 3.5 to offer real-time code suggestions, multi-file edits, and automatic commits, all within your terminal. In my upcoming presentation, I'll be showcasing how Aider can be used to create real, functional code while demonstrating its powerful capabilities. We’ll explore how this tool can make the impossible possible, whether you're refactoring, fixing bugs, or adding new features. Check out Aider on GitHub and learn more at https://aider.chat 🌐

- Event context: AI Tinkerers Fort Wayne August 20th 2024 Meet up — 2024-08-20 — Fort Wayne
- Public talk page: https://fort-wayne.aitinkerers.org/talks/rsvp_fd5h26pQoac

### [SotA on Function Calling with every LLM](https://seattle.aitinkerers.org/talks/rsvp_8L2s4NGdwZg)

We recently achieved state of the art results on the Berkley function calling benchmark with every model using a novel technique called SAP. Instead of improving the model, we worked on algorithms the refine the response of the model. The results: we can now beat naive function calling on Sonnet-3.5 or GPT4/4o with models like Haiku and GPT3.5.

- Event context: AI in Production Series - August 2024 — 2024-08-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_8L2s4NGdwZg

## Related Technologies

- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 518 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 654 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 171 public demos
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 178 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 185 public demos
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 111 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 187 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 444 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 204 public demos
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 73 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 96 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 88 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [DeepSeek](https://aitinkerers.org/technologies/deepseek) ([Markdown](https://aitinkerers.org/technologies/deepseek.md)) — 12 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 144 public demos

## More Results

- Previous: https://aitinkerers.org/technologies/gpt-4o.md
- Next: https://aitinkerers.org/technologies/gpt-4o.md?page=3